CN112966493A - Knowledge graph construction method and system - Google Patents
Knowledge graph construction method and system Download PDFInfo
- Publication number
- CN112966493A CN112966493A CN202110179910.0A CN202110179910A CN112966493A CN 112966493 A CN112966493 A CN 112966493A CN 202110179910 A CN202110179910 A CN 202110179910A CN 112966493 A CN112966493 A CN 112966493A
- Authority
- CN
- China
- Prior art keywords
- identification information
- statement
- video stream
- knowledge graph
- audio stream
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 30
- 230000000295 complement effect Effects 0.000 claims abstract description 17
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 10
- 230000015654 memory Effects 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 description 23
- 230000009471 action Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012552 review Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application relates to a knowledge graph construction method and a knowledge graph construction system, wherein the method comprises the steps of responding to an obtained audio stream or video stream, and converting the audio stream or the video stream into sentences; decomposing the composition of the sentence, wherein the decomposed content comprises a fixed term, a subject, a state, a predicate, an object and a complement; analyzing the meaning of the statement and positioning the identification information in the statement according to the decomposition result, wherein the number of the identification information is multiple, and the identification information comprises a subject and/or an object; analyzing the meaning of the statement and positioning the associated information in the statement, wherein the associated information comprises a fixed phrase, a subject, a predicate and a complement; establishing a connection relation between identification information according to the association information and establishing a knowledge graph according to the identification information and the connection relation between the identification information; wherein, the same identification information is subjected to merging processing. The method and the device can comb the contents of videos or sound recordings, and embody the key contents and the relation among all parts in the form of maps.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a knowledge graph construction method and system.
Background
The teacher can record or record the video to the lecture content at the lecture in-process, makes things convenient for the student to study again under class, but these audio frequency or video lack holistic summarization, can not embody the key content of lecture and the relation between each part.
Disclosure of Invention
The application provides a knowledge graph construction method and a knowledge graph construction system, which can be used for combing the contents of videos or sound recordings and embodying the key contents and the relation among all parts in the form of a graph.
In a first aspect, the present application provides a method for constructing a knowledge graph, including:
responding to the acquired audio stream or video stream, and converting the audio stream or video stream into a sentence;
decomposing the composition of the sentence, wherein the decomposed content comprises a fixed term, a subject, a state, a predicate, an object and a complement;
analyzing the meaning of the statement and positioning the identification information in the statement according to the decomposition result, wherein the number of the identification information is multiple, and the identification information comprises a subject and/or an object;
analyzing the meaning of the statement and positioning the associated information in the statement, wherein the associated information comprises a fixed phrase, a subject, a predicate and a complement;
establishing a connection relation between identification information according to the association information; and
establishing a knowledge graph according to the identification information and the connection relation among the identification information;
wherein, the same identification information is subjected to merging processing.
By adopting the technical scheme, the main content of the audio or the video and the contact among all the parts can be screened out, and the main content and the contact among all the parts are embodied in a knowledge graph mode.
In a possible implementation manner of the first aspect, the number of the audio streams or the video streams is multiple;
the merging process is performed for the same identification information appearing in different audio streams or video streams.
By adopting the technical scheme, a plurality of audio streams or video streams can be arranged, so that students can conveniently review the audio streams or the video streams in a targeted manner, and teachers can conveniently summarize the audio streams or the video streams.
In a possible implementation manner of the first aspect, the connection relationship includes a parallel relationship in which no direct connection relationship exists between the identification information and a hierarchical relationship in which a direct connection relationship exists between the identification information.
By adopting the technical scheme, the type of the connection relation is limited, and the composition of the knowledge graph can be simpler.
In a possible implementation manner of the first aspect, the method further includes:
numbering the acquired audio stream or video stream;
recording the address of each piece of identification information, wherein the address comprises the number of the audio stream or the video stream in which the identification information appears and the time of the audio stream or the video stream in which the identification information appears; and
and associating the address to the corresponding identification information in the knowledge graph.
By adopting the technical scheme, the corresponding audio stream or video stream can be found through the identification information, so that the user can conveniently and quickly position.
In a second aspect, the present application provides a knowledge-graph constructing apparatus, comprising:
the first processing unit is used for responding to the acquired audio stream or video stream and converting the audio stream or video stream into sentences;
the second processing unit is used for decomposing the composition of the sentence, and the decomposed content comprises a fixed term, a subject, a state, a predicate, an object and a complement;
the first analysis unit is used for analyzing the meaning of the statement and positioning the identification information in the statement according to the decomposition result, the number of the identification information is multiple, and the identification information comprises a subject and/or an object;
the second analysis unit is used for analyzing the meaning of the statement and positioning the associated information in the statement, wherein the associated information comprises a fixed term, a subject, a predicate and a complement;
the third processing unit is used for establishing the connection relation among the identification information according to the association information; and
and the fourth processing unit is used for establishing a knowledge graph according to the identification information and the connection relation among the identification information and carrying out merging processing on the same identification information.
In one possible implementation manner of the second aspect, the number of the audio streams or the video streams is multiple;
the merging process is performed for the same identification information appearing in different audio streams or video streams.
In a possible implementation manner of the second aspect, the connection relationship includes a parallel relationship in which no direct connection relationship exists between the identification information and a hierarchical relationship in which a direct connection relationship exists between the identification information.
In a possible implementation manner of the second aspect, the method further includes:
the numbering unit is used for numbering the acquired audio stream or video stream;
a recording unit for recording an address of each identification information, the address including a number of an audio stream or a video stream in which the identification information appears and a time when the identification information appears in the audio stream or the video stream; and
and the association unit is used for associating the address to the corresponding identification information in the knowledge graph.
In a third aspect, the present application provides a display content identification system, the system comprising:
one or more memories for storing instructions; and
one or more processors configured to call and execute the instructions from the memory, and perform the method for constructing a knowledge graph as described in the first aspect and any possible implementation manner of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium comprising:
a program that, when executed by a processor, performs a method of knowledge-graph construction as described in the first aspect and any possible implementation manner of the first aspect.
In a fifth aspect, the present application provides a computer program product comprising program instructions that, when executed by a computing device, perform a method of knowledge-graph construction as described in the first aspect and any possible implementation manner of the first aspect.
In a sixth aspect, the present application provides a system on a chip comprising a processor configured to perform the functions recited in the above aspects, such as generating, receiving, sending, or processing data and/or information recited in the above methods.
The chip system may be formed by a chip, or may include a chip and other discrete devices.
In one possible design, the system-on-chip further includes a memory for storing necessary program instructions and data. The processor and the memory may be decoupled, disposed on different devices, connected in a wired or wireless manner, or coupled on the same device.
Drawings
Fig. 1 is a schematic block diagram of a process for converting, decomposing and parsing an audio stream or a video stream according to an embodiment of the present application.
Fig. 2 is a block diagram illustrating a structure of a knowledge-graph according to an embodiment of the present disclosure.
Fig. 3 is a block diagram schematically illustrating the structure of another knowledge-graph based on fig. 2.
Detailed Description
The technical solution of the present application will be described in further detail below with reference to the accompanying drawings.
The knowledge graph construction method disclosed by the embodiment of the application mainly aims to comb the teaching contents of teachers, and on one hand, students can conveniently review the teaching contents in a targeted mode, and on the other hand, teachers can comb and summarize the teaching contents.
Taking a specific scene as an example, a teacher prepares courses according to reference contents such as a teaching outline, but considering understanding conditions of different people and reality in the course, a situation that the actual teaching content deviates from the teaching outline can occur; from the perspective of students, the comprehension ability of the students is different, and the lecture contents can be partially understood, and the emphasis and difficulty can be difficult to grasp without guidance.
Referring to fig. 1 and fig. 2, a method for constructing a knowledge graph disclosed in an embodiment of the present application mainly includes the following steps:
s101, responding to the acquired audio stream or video stream, and converting the audio stream or video stream into a sentence;
s102, decomposing the composition of the sentence, wherein the decomposed content comprises a fixed term, a subject, a predicate, an object and a complement;
s103, analyzing the meaning of the sentence and positioning a plurality of pieces of identification information according to the decomposition result, wherein the identification information comprises a subject and/or an object;
s104, analyzing the meaning of the statement and positioning the associated information in the statement, wherein the associated information comprises a fixed phrase, a subject, a predicate and a complement;
s105, establishing a connection relation between identification information according to the association information; and
s106, establishing a knowledge graph according to the identification information and the connection relation among the identification information;
wherein, the same identification information is subjected to merging processing.
The method for constructing the knowledge graph can be applied to a server, a computer, a mobile phone or other similar terminals, lecture contents are stored in a video or audio mode and then are sent to the terminal where the method for constructing the knowledge graph shown in the embodiment exists, and the video or audio of the lecture contents are analyzed and processed by the terminal, and then the lecture contents are presented in a knowledge graph mode.
Specifically, in step S101, in response to the acquired audio stream or video stream, the terminal converts the audio stream or video stream into a sentence, and then performs a subsequent analysis process.
It should be understood that the video stream is composed of two parts, i.e., a video stream providing video and an audio stream providing sound, and for the video stream, the audio stream can be separated and processed.
It should also be understood that the audio stream is an embodiment of text, and the obtained audio stream may be processed by using speech recognition and text conversion, and after the conversion is completed, the subsequent processing steps are performed.
In step S102, the composition of the sentence is decomposed, the decomposed contents include a predicate, a subject, a state, a predicate, an object, and a complement, and the decomposition is performed to understand the meaning of the sentence.
The words in step S101 are composed of sentences for which the machine cannot directly understand at all, and the meaning of the sentence to be expressed needs to be understood by the analysis tool. For a sentence, it can be divided into six parts, respectively a predicate, a subject, a state, a predicate, an object, and a complement, which are specifically explained as follows:
the subject language, i.e., "the originator of the action" (in the subject-predicate structure) or "the object of the expression" (in the subject-system structure), is usually placed at the beginning of the sentence, and sometimes also at the middle or end of the sentence. Nouns and pronouns can be used as the subject; also phrases, infinitives; and may even be the entire sentence.
A predicate is the soul of a sentence, primarily used to "state the subject" or "indicate the action the subject issues".
The object is opposite to the subject and indicates the recipient of the action. Nouns, pronouns, numerators, and sentences can all be object (object clauses).
The phrase is intended to define a component of a sentence. All the components such as adjectives, numerals, pronouns and clauses (clauses of definite language) can be basically made into definite languages (except verbs). The fixed phrase before the modified word is called the preposed fixed phrase; otherwise, it is the postfix.
The function of the zhuang language is to transmit and modify, and the transmitted information includes: time, place, cause, purpose, result, manner, degree, etc., which is used to make the expression more voluminous and concrete.
The table language is mainly used to explain the nature, state, characteristics, etc. of the subject.
Through the decomposition of the sentence, the main information in the sentence can be found, and in a few specific examples:
the first is "what we say today is a trigonometric function", in this sentence, the subject is "we", the predicate is "say", the object is "trigonometric function", and from the perspective of relevance, the most important information in this sentence is "trigonometric function".
Second, "trigonometric function" includes sine function, cosine function and tangent function, "in this sentence, the subject is" trigonometric function, "the predicate is" including, "and the object is" sine function, cosine function and tangent function, "from the perspective of relevance, the most important information in this sentence is" trigonometric function "and" sine function, cosine function and tangent function.
As can be seen from the two examples, the key information for making the knowledge graph can be obtained by disassembling and analyzing the composition of the sentences.
After the structure of the sentence is decomposed, executing step S103 and step S104, in step S103, analyzing the meaning of the sentence and positioning the identification information therein, wherein the number of the identification information is multiple, and the identification information comprises a subject and/or an object; in step S104, the meaning of the sentence is analyzed and the related information is located, wherein the related information includes a fixed term, a subject, a predicate and a complement.
Through the steps S103 and S104, the key information in the converted text can be screened, and the relationship between the key information can also be determined, where the screened key information is referred to as identification information, and the relationship information between the identification information is referred to as association information.
It will be appreciated that for a class there is a vast amount of other information besides these key information, such as explanation exercises and questioning links, which can be directly ignored.
In some possible implementations, a filtering manner may be used, for example, for the key information, a key information database may be set, and the filtering may be performed by a comparison manner, and for the associated information, the processing may also be performed in this manner.
In other possible implementations, the analysis is performed using a neural network language model.
Then, step S105 is executed, in which a connection relationship between the identification information is established according to the association information, so as to connect the discrete identification information, so that a network-like structure can be formed and presented.
It should be understood that after the above decomposition and analysis, a plurality of pieces of identification information can be obtained, but these pieces of identification information are discrete, and cannot be used like an information island, and when they are connected together using the association information, the connection relationship of the identification information becomes clear.
Also, the associated information appears together with the identification information, for example, in the example given above, the associated information and the identification information appear in the same sentence, and therefore, the relationship between the identification information can be easily established based on the associated information.
Finally, step S106 is executed, in which a knowledge graph is established according to the identification information and the connection relationship between the identification information, that is, the contents in steps S101 to S105 are embodied in the form of the knowledge graph.
Meanwhile, in order to make the expression form of the knowledge graph more concise, for the same identification information, merging processing needs to be performed, and the above two examples are explained continuously, in the whole video stream or audio stream, the 'trigonometric function' appears many times, but for the knowledge graph, only one-time recording is needed, because the knowledge graph reflects one frame more than the whole content, and after the same identification information is merged, the knowledge graph can be clearer and more concise.
For students, the knowledge graph can be used for knowing main contents in a video stream or an audio stream, and the students can determine which contents are understood, which contents are not understood or which contents are omitted and are not noticed according to the actual conditions of the students.
For teachers, the content of the lectures can be combed through the knowledge graph, for example, which contents are spoken, which contents are not spoken, or which part is missed, and the like can be found, so that the teaching plan is convenient to adjust and perfect, and advantages and disadvantages in the teaching contents can be found in time.
On the whole, the knowledge graph construction method shown in the embodiment of the application can comb the content of audio streams and video streams generated in the course of lecturing by teachers, and embody the combed content in the form of the knowledge graph, so that on one hand, students can conveniently check for omissions, on the other hand, teachers can conveniently adjust and perfect own teaching plans, and the effect of improving lecturing effects is achieved.
As a specific embodiment of the method for constructing a knowledge graph provided by the application, the number of the audio streams or the video streams is multiple, and the same identification information appearing in different audio streams or video streams is subjected to merging processing.
In this way, multiple audio or video streams can be processed, for example, a week or month of a lesson, and the framework can be combed and then embodied in a knowledge-graph manner, which is significantly more suitable than the processing of a single audio or video stream. Since the content of the lecture should be continuous for a teacher.
By such a processing method, the knowledge map can contain more contents and be reflected more comprehensively.
In the process, because a plurality of identification information are obtained, when the same identification information appears in two audio streams or video streams, the two audio streams or video streams can be associated through the two identification information.
Similarly, in the association process, the identification information appearing in different audio streams or video streams is also subjected to the merging process, and in the merging process, other identification information associated with the identification information is also associated through the merged identification information.
As a specific embodiment of the knowledge graph construction method provided by the application, the connection relationship is limited, and the connection relationship is only used and includes a parallel relationship in which no direct connection relationship exists between the identification information and a hierarchical relationship in which a direct connection relationship exists between the identification information.
That is, in the final knowledge-graph, there are only two states of relationship and no relationship for the identification information. With such restrictions, the relationships exhibited in the knowledge graph are more direct and easy to understand.
Referring to fig. 3, as a specific embodiment of the method for constructing a knowledge graph, for a knowledge graph, the relevance between the knowledge graph and an audio stream or a video stream is increased, and specific processing steps are as follows:
s201, numbering the acquired audio stream or video stream;
s202, recording the address of each piece of identification information, wherein the address comprises the number of an audio stream or a video stream in which the identification information appears and the time of the audio stream or the video stream in which the identification information appears; and
s203, the address is associated to the corresponding identification information in the knowledge graph.
Specifically, in step S201, the number of the acquired audio stream or video stream is numbered, and then the address of each identification information is recorded, where the address includes the number of the audio stream or video stream where the identification information appears and the time when the identification information appears in the audio stream or video stream, that is, the content in step S202, which is described as a specific example,
the number of the audio streams or the video streams is five, and the numbers thereof are 001, 002, 003, 004 and 005, respectively, and one identification information appears at the tenth minute in the audio stream or the video stream with the number 001, the fifteenth minute in the audio stream or the video stream with the number 003 and the seventh minute in the audio stream or the video stream with the number 005, respectively, so that these contents, which may be referred to as addresses, are all associated with the corresponding identification information in the knowledge graph, that is, the contents in step S203.
At this time, the content in the knowledge graph is richer, because the content in the audio stream or the video stream can be combed, and a tracing function can be provided, for students, the corresponding audio stream or the video stream can be directly found for review; for the teacher, the specific addresses can be viewed, summarized and further improved.
Compared with pure carding, the mode capable of providing the retrospective mode can obviously provide more use scenes.
The embodiment of the present application further provides a knowledge graph constructing apparatus, including:
the first processing unit is used for responding to the acquired audio stream or video stream and converting the audio stream or video stream into sentences;
the second processing unit is used for decomposing the composition of the sentence, and the decomposed content comprises a fixed term, a subject, a state, a predicate, an object and a complement;
the first analysis unit is used for analyzing the meaning of the statement and positioning the identification information in the statement according to the decomposition result, the number of the identification information is multiple, and the identification information comprises a subject and/or an object;
the second analysis unit is used for analyzing the meaning of the statement and positioning the associated information in the statement, wherein the associated information comprises a fixed term, a subject, a predicate and a complement;
the third processing unit is used for establishing the connection relation among the identification information according to the association information; and
and the fourth processing unit is used for establishing a knowledge graph according to the identification information and the connection relation among the identification information and carrying out merging processing on the same identification information.
Further, the number of the audio streams or the video streams is multiple;
the merging process is performed for the same identification information appearing in different audio streams or video streams.
Further, the connection relationship includes a parallel relationship in which no direct connection relationship exists between the identification information and a hierarchical relationship in which a direct connection relationship exists between the identification information.
Further, the following are also added:
the numbering unit is used for numbering the acquired audio stream or video stream;
a recording unit for recording an address of each identification information, the address including a number of an audio stream or a video stream in which the identification information appears and a time when the identification information appears in the audio stream or the video stream; and
and the association unit is used for associating the address to the corresponding identification information in the knowledge graph.
In one example, the units in any of the above apparatuses may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
As another example, when a unit in a device may be implemented in the form of a processing element scheduler, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of invoking programs. As another example, these units may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Various objects such as various messages/information/devices/network elements/systems/devices/actions/operations/procedures/concepts may be named in the present application, it is to be understood that these specific names do not constitute limitations on related objects, and the named names may vary according to circumstances, contexts, or usage habits, and the understanding of the technical meaning of the technical terms in the present application should be mainly determined by the functions and technical effects embodied/performed in the technical solutions.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It should also be understood that, in various embodiments of the present application, first, second, etc. are used merely to indicate that a plurality of objects are different. For example, the first time window and the second time window are merely to show different time windows. And should not have any influence on the time window itself, and the above-mentioned first, second, etc. should not impose any limitation on the embodiments of the present application.
It is also to be understood that the terminology and/or the description of the various embodiments herein is consistent and mutually inconsistent if no specific statement or logic conflicts exists, and that the technical features of the various embodiments may be combined to form new embodiments based on their inherent logical relationships.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a computer-readable storage medium, which includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned computer-readable storage media comprise: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Embodiments of the present application also provide a computer program product, which includes instructions that, when executed, cause the terminal device and the network device to perform operations corresponding to the terminal device and the network device of the above-mentioned methods.
An embodiment of the present application further provides a display content identification system, where the system includes:
one or more memories for storing instructions; and
one or more processors configured to retrieve and execute the instructions from the memory to perform the method of knowledge-graph construction as described above.
Embodiments of the present application further provide a chip system, which includes a processor, and is configured to implement the functions referred to in the foregoing, for example, to generate, receive, transmit, or process data and/or information referred to in the foregoing methods.
The chip system may be formed by a chip, or may include a chip and other discrete devices.
The processor mentioned in any of the above may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the method for transmitting feedback information.
In one possible design, the system-on-chip further includes a memory for storing necessary program instructions and data. The processor and the memory may be decoupled, respectively disposed on different devices, and connected in a wired or wireless manner to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory may be coupled to the same device.
Optionally, the computer instructions are stored in a memory.
Alternatively, the memory is a storage unit in the chip, such as a register, a cache, and the like, and the memory may also be a storage unit outside the chip in the terminal, such as a ROM or other types of static storage devices that can store static information and instructions, a RAM, and the like.
It will be appreciated that the memory in the embodiments of the subject application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory.
The non-volatile memory may be ROM, Programmable Read Only Memory (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), or flash memory.
Volatile memory can be RAM, which acts as external cache memory. There are many different types of RAM, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), synclink DRAM (SLDRAM), and direct memory bus RAM.
The embodiments of the present invention are preferred embodiments of the present application, and the scope of protection of the present application is not limited by the embodiments, so: all equivalent changes made according to the structure, shape and principle of the present application shall be covered by the protection scope of the present application.
Claims (10)
1. A knowledge graph construction method is characterized by comprising the following steps:
responding to the acquired audio stream or video stream, and converting the audio stream or video stream into a sentence;
decomposing the composition of the sentence, wherein the decomposed content comprises a fixed term, a subject, a state, a predicate, an object and a complement;
analyzing the meaning of the statement and positioning the identification information in the statement according to the decomposition result, wherein the number of the identification information is multiple, and the identification information comprises a subject and/or an object;
analyzing the meaning of the statement and positioning the associated information in the statement, wherein the associated information comprises a fixed phrase, a subject, a predicate and a complement;
establishing a connection relation between identification information according to the association information; and
establishing a knowledge graph according to the identification information and the connection relation among the identification information;
wherein, the same identification information is subjected to merging processing.
2. The method of claim 1, wherein the number of the audio streams or the video streams is plural;
the merging process is performed for the same identification information appearing in different audio streams or video streams.
3. The method according to claim 1 or 2, wherein the connection relationship comprises a parallel relationship in which no direct connection relationship exists between the identification information and a hierarchical relationship in which a direct connection relationship exists between the identification information.
4. The method of constructing a knowledge graph according to claim 2, further comprising:
numbering the acquired audio stream or video stream;
recording the address of each piece of identification information, wherein the address comprises the number of the audio stream or the video stream in which the identification information appears and the time of the audio stream or the video stream in which the identification information appears; and
and associating the address to the corresponding identification information in the knowledge graph.
5. A knowledge-graph building apparatus, comprising:
the first processing unit is used for responding to the acquired audio stream or video stream and converting the audio stream or video stream into sentences;
the second processing unit is used for decomposing the composition of the sentence, and the decomposed content comprises a fixed term, a subject, a state, a predicate, an object and a complement;
the first analysis unit is used for analyzing the meaning of the statement and positioning the identification information in the statement according to the decomposition result, the number of the identification information is multiple, and the identification information comprises a subject and/or an object;
the second analysis unit is used for analyzing the meaning of the statement and positioning the associated information in the statement, wherein the associated information comprises a fixed term, a subject, a predicate and a complement;
the third processing unit is used for establishing the connection relation among the identification information according to the association information; and
and the fourth processing unit is used for establishing a knowledge graph according to the identification information and the connection relation among the identification information and carrying out merging processing on the same identification information.
6. The apparatus according to claim 5, wherein the number of the audio streams or the video streams is plural;
the merging process is performed for the same identification information appearing in different audio streams or video streams.
7. The apparatus according to claim 5 or 6, wherein the connection relationship comprises a parallel relationship in which no direct connection relationship exists between the identification information and a hierarchical relationship in which a direct connection relationship exists between the identification information.
8. The apparatus of claim 5 or 6, further comprising:
the numbering unit is used for numbering the acquired audio stream or video stream;
a recording unit for recording an address of each identification information, the address including a number of an audio stream or a video stream in which the identification information appears and a time when the identification information appears in the audio stream or the video stream; and
and the association unit is used for associating the address to the corresponding identification information in the knowledge graph.
9. A display content recognition system, the system comprising:
one or more memories for storing instructions; and
one or more processors configured to retrieve and execute the instructions from the memory to perform the method of knowledge-graph construction of any one of claims 1 to 4.
10. A computer-readable storage medium, the computer-readable storage medium comprising:
a program which, when executed by a processor, performs the method of knowledge-graph construction according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110179910.0A CN112966493A (en) | 2021-02-07 | 2021-02-07 | Knowledge graph construction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110179910.0A CN112966493A (en) | 2021-02-07 | 2021-02-07 | Knowledge graph construction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112966493A true CN112966493A (en) | 2021-06-15 |
Family
ID=76284606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110179910.0A Pending CN112966493A (en) | 2021-02-07 | 2021-02-07 | Knowledge graph construction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112966493A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114390331A (en) * | 2022-01-13 | 2022-04-22 | 徐州工业职业技术学院 | Video teaching method, system, equipment and medium |
| CN116501892A (en) * | 2023-05-06 | 2023-07-28 | 广州番禺职业技术学院 | Training knowledge graph construction method based on automatic following system of Internet of things |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106462607A (en) * | 2014-05-12 | 2017-02-22 | 谷歌公司 | Automated reading comprehension |
| CN107545000A (en) * | 2016-06-28 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
| CN107545791A (en) * | 2017-08-29 | 2018-01-05 | 广州思涵信息科技有限公司 | A kind of system and method that classroom instruction knowledge mapping is automatically generated using courseware |
| CN107609478A (en) * | 2017-08-09 | 2018-01-19 | 广州思涵信息科技有限公司 | A kind of real-time analysis of the students system and method for matching classroom knowledge content |
| CN107633005A (en) * | 2017-08-09 | 2018-01-26 | 广州思涵信息科技有限公司 | A kind of knowledge mapping structure, comparison system and method based on class teaching content |
| CN109275046A (en) * | 2018-08-21 | 2019-01-25 | 华中师范大学 | A kind of teaching data mask method based on double video acquisitions |
| CN109902187A (en) * | 2019-03-21 | 2019-06-18 | 广东小天才科技有限公司 | Method and device for constructing characteristic knowledge graph and terminal equipment |
| CN110347798A (en) * | 2019-07-12 | 2019-10-18 | 之江实验室 | A kind of knowledge mapping auxiliary understanding system based on spatial term technology |
| CN110543574A (en) * | 2019-08-30 | 2019-12-06 | 北京百度网讯科技有限公司 | knowledge graph construction method, device, equipment and medium |
| CN110851610A (en) * | 2018-07-25 | 2020-02-28 | 百度在线网络技术（北京）有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
| CN111046656A (en) * | 2019-11-15 | 2020-04-21 | 北京三快在线科技有限公司 | Text processing method and device, electronic equipment and readable storage medium |
| CN111651690A (en) * | 2020-05-29 | 2020-09-11 | 深圳市天一智联科技有限公司 | Case-related information searching method and device and computer equipment |
-
2021
- 2021-02-07 CN CN202110179910.0A patent/CN112966493A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106462607A (en) * | 2014-05-12 | 2017-02-22 | 谷歌公司 | Automated reading comprehension |
| CN107545000A (en) * | 2016-06-28 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
| CN107609478A (en) * | 2017-08-09 | 2018-01-19 | 广州思涵信息科技有限公司 | A kind of real-time analysis of the students system and method for matching classroom knowledge content |
| CN107633005A (en) * | 2017-08-09 | 2018-01-26 | 广州思涵信息科技有限公司 | A kind of knowledge mapping structure, comparison system and method based on class teaching content |
| CN107545791A (en) * | 2017-08-29 | 2018-01-05 | 广州思涵信息科技有限公司 | A kind of system and method that classroom instruction knowledge mapping is automatically generated using courseware |
| CN110851610A (en) * | 2018-07-25 | 2020-02-28 | 百度在线网络技术（北京）有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
| CN109275046A (en) * | 2018-08-21 | 2019-01-25 | 华中师范大学 | A kind of teaching data mask method based on double video acquisitions |
| CN109902187A (en) * | 2019-03-21 | 2019-06-18 | 广东小天才科技有限公司 | Method and device for constructing characteristic knowledge graph and terminal equipment |
| CN110347798A (en) * | 2019-07-12 | 2019-10-18 | 之江实验室 | A kind of knowledge mapping auxiliary understanding system based on spatial term technology |
| CN110543574A (en) * | 2019-08-30 | 2019-12-06 | 北京百度网讯科技有限公司 | knowledge graph construction method, device, equipment and medium |
| CN111046656A (en) * | 2019-11-15 | 2020-04-21 | 北京三快在线科技有限公司 | Text processing method and device, electronic equipment and readable storage medium |
| CN111651690A (en) * | 2020-05-29 | 2020-09-11 | 深圳市天一智联科技有限公司 | Case-related information searching method and device and computer equipment |
Non-Patent Citations (2)
| Title |
|---|
| 李艳燕等: "面向智慧教育的学科知识图谱构建与创新应用", 《网络出版地址： HTTP://KNS.CNKI.NET/KCMS/DETAIL/62.1022.G4.20190725.0934.008.HTML》 * |
| 钟亮: "基于中文百科的初中数学学科知识图谱构建与应用", 《硕士学位论文全文数据库社会科学II辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114390331A (en) * | 2022-01-13 | 2022-04-22 | 徐州工业职业技术学院 | Video teaching method, system, equipment and medium |
| CN114390331B (en) * | 2022-01-13 | 2023-09-08 | 徐州工业职业技术学院 | Video teaching method, system, equipment and medium |
| CN116501892A (en) * | 2023-05-06 | 2023-07-28 | 广州番禺职业技术学院 | Training knowledge graph construction method based on automatic following system of Internet of things |
| CN116501892B (en) * | 2023-05-06 | 2024-03-29 | 广州番禺职业技术学院 | Training knowledge graph construction method based on automatic following system of Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| O’Halloran et al. | A digital mixed methods research design: Integrating multimodal analysis with data mining and information visualization for big data analytics | |
| Lester et al. | Learning to do qualitative data analysis: A starting point | |
| Krämer et al. | Culture, technology, cultural techniques–Moving beyond text1 | |
| Chandler et al. | Listening to voices and visualizing data in qualitative research: Hypermodal dissemination possibilities | |
| Cassidy et al. | Failing grade: 89% of introduction-to-psychology textbooks that define or explain statistical significance do so incorrectly | |
| Schrodt et al. | Political science: KEDS—a program for the machine coding of event data | |
| Mantie | A comparison of “popular music pedagogy” discourses | |
| Bucy et al. | The mediated moderation model of interactivity | |
| Tonkiss | Analysing text and speech: content and discourse analysis | |
| Bernauer et al. | Blending the old and the new: Qualitative data analysis as critical thinking and using NVivo with a generic approach | |
| Van Dijk | Discourse studies and hermeneutics | |
| Kapatsinski | Frequency of use leads to automaticity of production: Evidence from repair in conversation | |
| US10909986B2 (en) | Assessment of speech consumability by text analysis | |
| Friedman et al. | Nodes and arcs: concept map, semiotics, and knowledge organization | |
| CN112966493A (en) | Knowledge graph construction method and system | |
| Monreal | A move-step analysis of the concluding chapters in computer science PhD theses | |
| Zhang | Exploring personal metadiscourse markers across speech and writing using cluster analysis | |
| WO2022016226A1 (en) | Self-adapting and autonomous methods for analysis of textual and verbal communication | |
| Collard et al. | Predictors of ear-voice span, a corpus-based study with special reference to sex | |
| Beckers | The voice of the people in the news: A content analysis of public opinion displays in routine and election news | |
| Foucault | Linguistics and social sciences | |
| Baker et al. | How to use corpus linguistics in sociolinguistics: A case study of modal verb use, age and change over time | |
| Slaney | Why force a square peg into a round hole? The ongoing (pseudo-) problem of psychological measurement | |
| Su et al. | Framing overseas Chinese students: A comparative analysis of newspaper coverage in mainland China, US, and Hong Kong | |
| CN113050933B (en) | Brain graph data processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210615 |
|
| RJ01 | Rejection of invention patent application after publication |